JP5023874B2 - Color imaging device - Google Patents

Description

  The present invention relates to a color imaging apparatus equipped with a white balance adjustment function.

Japanese Patent Application Laid-Open No. 2004-151867 describes a method for determining the type of illumination used when photographing an image when calculating the amount of white balance adjustment to be performed on the image. This method calculates a discrimination criterion in advance by supervised learning using a specific color component (for example, R component) of an image as a feature amount, and based on the discrimination criterion and a feature amount extracted from each image, It is determined whether or not the illumination type of the object scene at the time of shooting is a specific type.
JP 2006-129442 A

  However, with this discrimination method, there is a high probability of erroneous discrimination when there are many object images having color components similar to an achromatic object illuminated with a specific type of illumination in the image.

  Accordingly, an object of the present invention is to provide a color imaging apparatus capable of grouping individual shooting scenes with high accuracy according to the illumination color.

  The color imaging apparatus of the present invention extracts a feature vector reflecting both the subject condition and the shooting condition of the shooting scene from the shooting scene to be discriminated, and calculates the feature vector in advance by supervised learning. And determining means for determining whether or not the shooting scene belongs to a specific group having a similar illumination color based on the determined determination criteria, and the vector component of the feature vector includes lens information of the shooting lens. It is characterized by that.
  Another color imaging apparatus of the present invention extracts a feature vector reflecting both the subject condition and the shooting condition of the shooting scene from the shooting scene to be discriminated, and the feature vector and supervised learning. Discrimination means for discriminating whether or not the shooting scene belongs to a specific group having similar illumination colors based on a discrimination criterion calculated in advance, and illumination at the time of shooting based on a color histogram of an image shot in the shooting scene An estimation unit configured to estimate a color, and the estimation unit limits a color range of the color histogram used for the estimation according to a result of determination performed by the determination unit.
  Another color imaging apparatus of the present invention extracts a feature vector reflecting both the subject condition and the shooting condition of the shooting scene from the shooting scene to be discriminated, and the feature vector and supervised learning. Based on a pre-determined discrimination criterion, it comprises discrimination means for discriminating whether or not the shooting scene belongs to a specific group having similar illumination colors, and the vector component of the feature vector contains the color of the object scene And the lens position of the photographing lens.
  Another color imaging apparatus of the present invention extracts a feature vector reflecting both the subject condition and the shooting condition of the shooting scene from the shooting scene to be discriminated, and the feature vector and supervised learning. Based on a pre-determined discrimination criterion, it comprises discrimination means for discriminating whether or not the photographic scene belongs to a specific group having similar illumination colors, and the discrimination means is a support vector machine.
  Another color imaging apparatus of the present invention extracts a feature vector reflecting both the subject condition and the shooting condition of the shooting scene from the shooting scene to be discriminated, and the feature vector and supervised learning. And determining means for determining whether or not the photographic scene belongs to a specific group having a similar illumination color based on a pre-determined determination criterion, wherein the determination means relates to each of a plurality of specific groups having different illumination colors. The discrimination is performed.

  The vector component of the feature vector preferably includes an edge amount existing in the scene.

  Further, it is desirable that the determination means perform the determination in a period before photographing.

  In addition, the determination unit may sequentially determine each of the plurality of specific groups, and if the determination result is “positive”, subsequent determination processing may be omitted.

  The plurality of specific groups include a group in which the illumination color belongs to a chromaticity range of low color temperature illumination, a group in which the illumination color belongs to a chromaticity range of a fluorescent lamp or a mercury lamp, and the illumination color has good color rendering. Any three of the groups belonging to the chromaticity range of fluorescent light or natural sunlight and the groups of the illumination color belonging to the shade or cloudy chromaticity range may be used.

  Further, the plurality of specific groups include a group in which the illumination color belongs to a chromaticity range of clear sky, a group in which the illumination color belongs to a shaded chromaticity range, and the illumination color of a low color temperature fluorescent lamp or a light bulb. A group that belongs to the range, a group that the illumination color belongs to the chromaticity range of the medium temperature fluorescent lamp, a group that the illumination color belongs to the chromaticity range of the high color temperature fluorescent lamp, and the chromaticity of the mercury lamp There may be any six of the groups belonging to the range and the groups having the illumination color belonging to the chromaticity range of the low color temperature illumination.

  The color imaging apparatus of the present invention further includes an estimation unit that estimates an illumination type at the time of shooting based on a color histogram of an image shot in the shooting scene, and the estimation unit includes a color range of the color histogram, You may restrict | limit according to the result of the discrimination | determination which the said discrimination means performed.

  Further, the image processing apparatus further includes an estimation unit that estimates an illumination type at the time of shooting based on a color histogram of an image shot in the shooting scene, and the estimation unit performs the determination unit on the frequency of each color range of the color histogram. Weighting may be performed according to the determination result.

  According to the present invention, individual shooting scenes can be grouped with high accuracy by their illumination colors.

[First Embodiment]
The present embodiment is an embodiment of an electronic camera. Here, it is assumed that the electronic camera is a single-lens reflex type.

  First, the photographing mechanism of the electronic camera will be described. FIG. 1 is a schematic diagram showing a configuration of an optical system of an electronic camera. As shown in FIG. 1, the electronic camera includes a camera body 11 and a lens unit 13 that houses a photographing lens 12. The lens unit 13 is replaceably attached to the camera body 11 via a mount (not shown).

  In the camera body 11, a main mirror 14, a mechanical shutter 15, a color image sensor 16, and a finder optical system (17 to 20) are arranged. The main mirror 14, the mechanical shutter 15, and the color image sensor 16 are disposed along the optical axis of the photographing lens 12, and the finder optical system (17 to 20) is disposed in the upper region of the camera body 11.

  The main mirror 14 rotates around a rotation shaft (not shown), and is thereby switched between an observation state and a retracted state. The main mirror 14 in the observation state is inclined and disposed in front of the mechanical shutter 15 and the color image sensor 16. The main mirror 14 in the observation state reflects the light beam captured by the photographing lens 12 upward and guides it to the finder optical system (17 to 20). The center of the main mirror 14 is a half mirror, and a part of the light beam transmitted through the main mirror 14 in the observation state is guided to a focus detection unit (not shown) by the sub mirror.

  On the other hand, the main mirror 14 in the retracted state is in a position that is flipped upward and off the photographing optical path. When the main mirror 14 is in the retracted state, the light beam captured by the photographing lens 12 is guided to the mechanical shutter 15 and the color image sensor 16.

  The finder optical system (17 to 20) includes a focusing screen 17, a condenser lens 18, a pentaprism 19, and an eyepiece lens 20. Among these, a re-imaging lens 21 and a split photometric sensor 22 are disposed in the vicinity of the pentaprism 19.

  The focusing screen 17 is located above the main mirror 14. The light beam formed on the focusing screen 17 enters the incident surface on the lower surface of the pentaprism 19 via the condenser lens 18. A part of the light beam incident on the incident surface is reflected from the inner surface of the pentaprism 19, exits from the exit surface perpendicular to the incident surface to the outside of the pentaprism 19, and travels toward the eyepiece lens 20.

  Further, another part of the light beam incident on the incident surface is reflected from the inner surface of the pentaprism 19 and then exits from the exit surface to the outside of the pentaprism 19, and is divided into photometric sensors via the re-imaging lens 21. To 22.

  Next, the circuit configuration of the electronic camera will be described. FIG. 2 is a block diagram showing a circuit configuration of the electronic camera. As shown in FIG. 2, the camera body 11 includes a color image sensor 16, an AFE 16a, a divided photometric sensor 22, an A / D conversion circuit 22a, an image processing circuit 23, a buffer memory (MEM) 24, and a recording interface. (Recording I / F) 25, operation switch (SW) 26, CPU 29, RAM 28, ROM 27, and bus 31 are provided. Among these, the image processing circuit 23, the buffer memory 24, the recording interface 25, the CPU 29, the RAM 28, and the ROM 27 are connected to each other via a bus 31. The operation switch 26 is connected to the CPU 29.

  The color image pickup device 16 is a color image pickup device provided for generating a recording image (main image). The color imaging device 16 generates an analog image signal of the main image by photoelectrically converting the object scene image formed on the imaging surface. Note that, on the imaging surface of the color imaging device 16, three types of color filters of red (R), green (G), and blue (B) are arranged in, for example, a Bayer array in order to detect the color of the object scene image. Has been. Therefore, the analog image signal of the main image is composed of three components of R component, G component, and B component.

  The AFE 16a is an analog front-end circuit that performs signal processing on an analog image signal generated by the color imaging device 16. The AFE 16a performs correlated double sampling of the image signal, adjustment of the gain of the image signal, and A / D conversion of the image signal. The image signal (digital image signal) output from the AFE 16a is input to the image processing circuit 23 as image data of the main image.

  The divided photometric sensor 22 is a color image sensor provided for monitoring the chromaticity distribution and brightness distribution of the object scene during non-shooting. An object scene image in the same range as that formed on the imaging surface of the color image sensor 16 is formed on the imaging surface of the split photometry sensor 22. The divided photometric sensor 22 photoelectrically converts the object scene image formed on the imaging surface thereof to generate an analog image signal of the object scene image. A color filter is disposed on the imaging surface of the split photometric sensor 22 for color detection of the object scene image. Therefore, the image signal of the object scene image is also composed of three components of R component, G component, and B component. The analog image signal of the object scene image output from the divided photometric sensor 22 is input to the CPU 29 via the A / D conversion circuit 22a.

  The image processing circuit 23 performs various image processing (color interpolation processing, gradation conversion processing, contour enhancement processing, white balance adjustment, etc.) on the image data of the main image input from the AFE 16a. The parameters (tone conversion characteristics, contour enhancement strength, white balance adjustment amount, etc.) of these processes are calculated as appropriate by the CPU 29. Of these, the white balance adjustment amount is composed of an R / G gain value and a B / G gain value.

  The buffer memory 24 temporarily stores the image data of the main image at a necessary timing during the operation of the image processing circuit 23 in order to compensate for a difference in speed of individual processing by the image processing circuit 23.

  The recording interface 25 is formed with a connector for connecting the storage medium 32. The recording interface 25 accesses the storage medium 32 connected to the connector, and writes and reads image data of the main image. The storage medium 32 is constituted by a hard disk, a memory card incorporating a semiconductor memory, or the like.

  The operation switch 26 is a release button, a command dial, a cross-shaped cursor key, and the like, and gives a signal to the CPU 29 according to the operation content by the user. For example, the user gives a shooting instruction to the CPU 29 by fully pressing the release button. In addition, the user gives an instruction to switch the recording mode to the CPU 29 by operating the operation switch 26.

  The recording mode includes a normal recording mode and a RAW recording mode. The normal recording mode is a recording mode in which the CPU 29 records the image data of the main image after image processing in the storage medium 32. The RAW recording mode is the CPU 29. Is a recording mode in which image data (RAW data) of a main image before image processing is recorded in the storage medium 32.

  The CPU 29 is a processor that performs overall control of the electronic camera. The CPU 29 reads out a sequence program stored in advance in the ROM 27 to the RAM 28 and executes the program to calculate parameters for each process and control each unit of the electronic camera. At this time, the CPU 29 captures lens information from a lens CPU (not shown) of the lens unit 13 as necessary. This lens information includes information such as the focal length of the photographing lens 12, the subject distance, and the aperture value.

Further, the CPU 29 functions as a support vector machine (SVM) that determines whether the current shooting scene belongs to the specific group D ₁ (first determination) by executing the program. The SVM also determines whether or not the current shooting scene belongs to another group D ₂ (second determination), and determines whether or not the current shooting scene belongs to group D ₃ (third Determination) can also be performed.

Here, the group D ₁ , the group D ₂ , and the group D ₃ are groups in which various shooting scenes can be grouped according to their illumination colors. Further, each discrimination criterion of the first discrimination, the second discrimination, and the third discrimination by the SVM is calculated in advance by the supervised learning by the SVM. These discrimination criteria are stored in the ROM 27 in advance as data of the discrimination surfaces S ₁ , S ₂ , S ₃ .

Next, each group will be described in detail. FIG. 3 shows various achromatic color detection ranges on chromaticity coordinates. The achromatic color detection range data is stored in advance in the ROM 27. These achromatic color detection ranges include the following achromatic color detection ranges C _L , C _SSL , C _FL1 , C _FL2 , C _HG , C _S , C _CL , and C _SH distributed in the vicinity of the black body radiation locus.

Achromatic color detection range C _L ... Chromaticity range of a light bulb (= chromaticity range of an achromatic object illuminated by a light bulb).

Achromatic color detection range C _SSL ... Chromaticity range of sunset (= chromaticity range of an achromatic object illuminated by sunset).

Achromatic color detection range C _FL1 ... Chromaticity range of the first fluorescent lamp (= chromaticity range of the achromatic object illuminated by the first fluorescent lamp).

Achromatic color detection range C _FL2 ... The chromaticity range of the second fluorescent lamp (= the chromaticity range of the achromatic object illuminated by the second fluorescent lamp).

Achromatic detection range C _HG ... The chromaticity range of a mercury lamp (= chromaticity range of an achromatic object illuminated with a mercury lamp).

Achromatic color detection range C _S .. chromaticity range in fine weather (= chromaticity range of an achromatic object existing under fine weather). If the color rendering property is good, the chromaticity of the fluorescent lamp also belongs to this chromaticity range.

Achromatic color detection range C _CL ... Chromatic chromaticity range (= chromaticity range of an achromatic object existing under cloudy weather).

Achromatic color detection range C _SH ... shaded chromaticity range (= chromaticity range of an achromatic object existing in the shade).

The groups D ₁ , D ₂ and D ₃ are the following groups.

Group D ₁ : A group of shooting scenes in which the illumination color belongs to one of the achromatic color detection ranges C _L and C _SSL having a relatively low color temperature.

Group D ₂ ... A group of shooting scenes in which the illumination color belongs to one of the achromatic color detection ranges C _FL1 , C _FL2 , and C _HG .

Group D ₃ ... A group of shooting scenes in which the illumination color belongs to the achromatic color detection range C _S.

Groups D ₄ and D ₀ are defined as follows.

Group D ₄ ... A group of shooting scenes in which the illumination color belongs to either the achromatic color detection range C _CL or C _SH .

Group D ₀ ... A group of shooting scenes in which the illumination color belongs to any one of the achromatic color detection ranges C _L , C _SSL , C _FL1 , C _FL2 , C _HG , C _S , C _CL , C _SH .

Next, the content of supervised learning for calculating the identification surfaces S ₁ , S ₂ , S ₃ will be described.

The learning samples used in this learning are a large number of shooting scenes that can be assumed for an electronic camera. Each learning sample is labeled as belonging to one of group D ₁ , group D ₂ , group D ₃ , or group D ₄ by the manufacturer of the electronic camera.

From each learning sample, a 15th-order feature vector having vector components x ₁ , x ₂ ,..., X ₁₅ is extracted. Each vector component x ₁ , x ₂ ,..., X ₁₅ consists of the following quantities:

x ₁ = average Bv value of the object scene,
x ₂ = maximum Bv value of the scene,
x ₃ = minimum Bv value of the scene,
x ₄ = standard deviation of the Bv value of the object scene,
x ₅ = average B / G value of the field,
x ₆ = maximum B / G value of the field,
x ₇ = minimum B / G value of the field,
x ₈ = standard deviation of the B / G value of the object scene,
x ₉ = average R / G value of the field,
x ₁₀ = maximum R / G value of the field,
x ₁₁ = minimum R / G value of the field,
x ₁₂ = standard deviation of R / G value of the field,
x ₁₃ = the amount of edges existing in the object scene,
x ₁₄ = focal length of the taking lens,
x ₁₅ = Subject distance of the taking lens Of these, vector components x _{1 to} x ₁₃ are calculated based on the image signal generated by the split photometric sensor 22. On the other hand, the vector components x ₁₄ and x ₁₅ are determined by lens information fetched from the lens CPU. Furthermore, the vector components x ₁₃ is calculated as follows.

First, edge filter processing in the X direction and edge filter processing in the Y direction are performed on the G component of the image signal generated by the divided photometric sensor 22. Thereby, the edge amount in the X direction and the edge amount in the Y direction of the object scene are calculated. Then, the sum of the edge amount in the X direction and the edge amount in the Y direction is calculated. The sum is the vector component x ₁₃ .

In learning, feature quantity vectors of all learning samples are represented by points on the vector space. Among these, the feature amount vector of each learning sample belonging to the group D ₁ and the feature amount vector of each learning sample not belonging to the group D ₁ have different distribution regions as shown by dotted lines in FIG. In FIG. 4, for the sake of simplicity, the 15-dimensional vector space P is represented in two dimensions.

Next, a learning sample belonging to the group D _1, margin between the learning samples that do not belong to the group D ₁ is the hyperplane such that the maximum is calculated, the hyperplane is a discriminant plane S _1. The data of the identification surface S ₁ is written in the ROM 27.

Here, as shown in FIG. 4, the Euclidean distance d ₁ from the identification plane S ₁ to each learning sample is considered. The polarity of the distance d ₁ takes the side where many learning samples that do not belong to the group D ₁ is distributed positive and negative side many training samples belonging to the group D ₁ is distributed.

FIG. 5 is a diagram showing the relationship between the distance d ₁ and the number of samples m. As shown in FIG. 5, the number of training samples belonging to the group D ₁ becomes the distance d ₁ is negative, many learning samples that do not belong to the group D ₁ becomes the distance d ₁ positive, also belonging to the group D ₁ and the distance d ₁ positive become such training samples despite the distance d ₁ despite not belonging to group D ₁ is also present learning samples as negative. Here, the range Zg ₁ of the distance d ₁ of such learning samples is referred to as “gray zone Zg ₁ ”.

Therefore, in the present embodiment, when the identification surface S ₁ is calculated, a positive boundary value Th _pos1 and a negative boundary value Th _{neg1 of the} gray zone Zg ₁ are calculated in _advance . Data of these boundary values Th _pos1 and Th _neg1 are also written in the ROM 27 together with the data of the identification surface S ₁ .

Next, a learning sample belonging to the group D ₂ in a vector space P, the margin between the learning samples that do not belong to the group D ₂ is calculated hyperplane such that maximum, the hyperplane discriminant plane S ₂ It is said. Further, the identification surface S gray area Zg ₂ in the vicinity of ₂ is calculated, the boundary value Th _pos2 the positive side of the gray area Zg _2, the boundary value Th _Neg2 the minus side is calculated (see FIG. 6). Data of these identification surface S ₂ , boundary values Th _pos2 , Th _neg2 is written in the ROM 27.

Next, a learning sample belonging to the group D ₃ in a vector space P, the margin between the learning samples that do not belong to the group D ₃ is calculated hyperplane such that maximum, the hyperplane discriminant plane S ₃ It is said. Further, the calculated identification surface gray area Zg ₃ in the vicinity of the S _3, the boundary value Th _pos3 the positive side of the gray area Zg _3, the boundary value Th _Neg3 the minus side is calculated (see FIG. 7). The data of the identification surface S ₃ , boundary values Th _pos3 , Th _neg3 is written in the ROM 27.

  Next, the flow of operation of the CPU 29 relating to shooting will be described. FIG. 8 is an operation flowchart of the CPU 29 regarding photographing. Here, it is assumed that the auto white balance function of the electronic camera is turned on and the recording mode of the electronic camera is set to the normal recording mode. At the start of the flowchart, the main mirror 14 is in the observation state, and the user can observe the object scene from the eyepiece 20.

  Step S101: The CPU 29 determines whether or not the release button is half-pressed. If the release button is half-pressed, the process proceeds to step S102, and if the release button is not half-pressed, the step S101 is repeated.

  Step S102: The CPU 29 performs focus adjustment of the photographing lens 12, and causes the split photometric sensor 22 to start outputting an image signal of the object scene. The focus adjustment is performed when the CPU 29 gives a defocus signal generated by the focus detection unit to the lens CPU. At this time, the lens CPU changes the lens position of the photographic lens 12 so that the defocus signal supplied from the CPU 29 approaches zero, and thereby focuses the photographic lens 12 on an object (subject) in the object field.

  Step S103: The CPU 29 extracts a feature vector from the current shooting scene by using the SVM function. This extraction is performed based on the image signal of the object scene output from the divided photometric sensor 22 and lens information (lens information after focus adjustment) given from the lens CPU. The feature vector is a feature vector having the same vector component as the feature vector extracted at the time of learning.

Step S104: The CPU 29 calculates a distance d ₁ between the feature vector extracted in step S103 and the identification surface S ₁ by the SVM function (first determination). As this distance d ₁ is small, the accuracy of the current shooting scene belongs to the group D ₁ is high, as the distance d ₁ is larger, the accuracy of the current shooting scene belongs to the group D ₁ is low.

Step S105: CPU 29 compares the distance d ₁ and the boundary value Th _neg1 calculated in step S104, it is determined whether expression of d ₁ <Th _neg1 is satisfied. When this expression is satisfied, the distance d ₁ of the current shooting scene is located on the minus side of the gray zone Zg ₁ (see FIG. 5). Therefore CPU209, the current shooting scene If this expression is satisfied migrates regarded as belonging to the group D ₁ to step S106, if the expression is not satisfied, the process proceeds to step S107 to perform the following determination.

  Step S106: The CPU 29 sets the group number i of the current shooting scene to “1”, and proceeds to step S116.

Step S107: CPU 29 by the function of the SVM, the feature vector extracted in step S103 and calculates the distance d ₂ between the identification surface S ₂ (second determination). As this distance d ₂ is small, the accuracy of the current shooting scene belongs to the group D ₂ is high, as the distance d ₂ is greater, the accuracy of the current shooting scene belongs to the group D ₂ is low.

Step S108: CPU 29 compares the distance d ₂ and boundary value Th _Neg2 calculated in step S107, it is determined whether expression of d _{2 <Th} neg2 is satisfied. When this equation is satisfied, the distance d ₂ of the current shooting scene is located on the minus side of the gray zone Zg ₂ (see FIG. 6). Therefore CPU209, the current shooting scene If this expression is satisfied, the process proceeds to step S109 is regarded as belonging to the group D _2, if this equation is not satisfied, the process proceeds to step S110 to perform the following determination.

  Step S109: The CPU 29 sets the group number i of the current shooting scene to “2”, and proceeds to step S116.

Step S110: The CPU 29 calculates a distance d ₃ between the feature vector extracted in step S103 and the identification surface S ₃ by the function of the SVM (third discrimination). As this distance d ₃ is small, the accuracy of the current shooting scene belongs to the group D ₃ is high, as the distance d ₃ large, the accuracy of the current shooting scene belongs to the group D ₃ is low.

Step S 111: CPU 29 compares the distance d ₃ and boundary value Th _Neg3 calculated in step S110, it is determined whether expression of d _{3 <Th} neg3 is satisfied. When this equation is satisfied, the distance d ₃ of the current shooting scene is located on the minus side of the gray zone Zg ₃ (see FIG. 7). Therefore, the CPU 209 regards the current shooting scene as belonging to the group D ₃ when this equation is satisfied, and proceeds to step S112. If this equation is not satisfied, the CPU 209 proceeds to step S113.

  Step S112: The CPU 29 sets the group number i of the current shooting scene to “3”, and proceeds to step S116.

Step S113: The CPU 29 compares the distances d ₁ , d ₂ and d ₃ calculated in each of steps S104, S107 and S110 with the boundary values Th _pos1 , Th _pos2 and Th _pos3 and all of the following expressions are satisfied. It is determined whether or not.

Th _pos1 <d ₁ , Th _pos2 <d ₂ , Th _pos3 <d ₃
When all of these expressions are satisfied, the distance d ₁ of the current shooting scene is located on the plus side of the gray zone Zg ₁ (see FIG. 5), and the distance d ₂ of the current shooting scene is the gray zone Zg ₂ ( located on the plus side in FIG see 6), and the distance d ₃ of the present shooting scene will have been positioned on the positive side of the gray area Zg _3. Therefore, the CPU 29 regards the current shooting scene as belonging to the group D ₄ when this expression is satisfied, and proceeds to step S114. If not satisfied, the CPU 29 regards the current shooting scene as belonging to the group D ₀ (ie. , Assuming that group discrimination is impossible), the process proceeds to step S115.

  Step S114: The CPU 29 sets the group number i of the current shooting scene to “4”, and proceeds to step S116.

  Step S115: The CPU 29 sets the group number i of the current shooting scene to “0”, and proceeds to step S116.

  Step S116: The CPU 29 determines whether or not the release button has been fully pressed. If the release button is not fully pressed, the process proceeds to S117, and if the release button is fully pressed, the process proceeds to S118.

  Step S117: The CPU 29 determines whether or not the half-press of the release button has been released. If the half-press of the release button has been released, the CPU 29 stops the signal output of the divided photometric sensor 22 and returns to step S101. If the half-press of the release button continues, the process returns to step S103.

  Step S118: The CPU 29 executes an imaging process and acquires image data of the main image. That is, the CPU 29 acquires the image data of the main image by moving the main mirror 14 to the retracted position and driving the color imaging device 16. The actual image data passes through the AFE 16 a and the image processing unit 23 in a pipeline manner, and is then buffered in the buffer memory 24. When the photographing process is completed, the main mirror 14 is returned to the observation position.

  Step S119: The CPU 29 determines the white balance adjustment amount of white balance adjustment to be applied to the image data of the main image acquired in step S118 according to the following procedures (1) to (5) according to the group number i being set. calculate.

(1) The CPU 29 restricts the achromatic color detection range (FIG. 3) defined on the chromaticity coordinates to only those corresponding to the group number i currently set. That is, when the group number i is “1”, the achromatic color detection ranges other than the achromatic color detection ranges C _L and C _SSL are invalidated, and when the group number i is “2”, the achromatic color detection is performed. When the achromatic color detection range other than the ranges C _FL1 , C _FL2 , and C _HG is invalidated and the group number i is “3”, the achromatic color detection range other than the achromatic color detection range C _S is invalidated, and the group number When i is “4”, the achromatic color detection ranges other than the achromatic color detection ranges C _CL and C _SH are invalidated, and when the group number i is “0”, all achromatic color detection areas are set. Enable

  (2) The CPU 29 divides the main image into a plurality of small areas, calculates the chromaticity of each small area (average chromaticity in the small area), and converts each small area according to the chromaticity. Map onto the coordinates. Further, the CPU 29 finds small areas mapped to the effective achromatic color detection range in each small area, and calculates the number (frequency) of these small areas for each achromatic color detection range. As a result, a color histogram relating to an effective achromatic color detection range is created.

For example, as illustrated in FIG. 9, the color histogram created when the group number i is “1” is the color histogram H ₁ related only to the achromatic color detection ranges C _L and C _SSL , and the group number i is “ 2 ”is a color histogram H ₂ relating only to the achromatic color detection ranges C _FL1 , C _FL2 , and C _HG , and is generated when the group number i is“ 3 ”. The color histogram is a color histogram H ₃ related only to the achromatic color detection range C _S , and the color histogram created when the group number i is “4” is a color related to only the achromatic color detection ranges C _CL and C _SH. Histogram H ₄ . Further, the color histogram created when the group number i is “0” indicates that all the achromatic color detection ranges C _L , C _SSL , C _FL1 , C _FL2 , C _HG , C _S , C _CL , C _SH Is a color histogram H ₀ for.

(3) The CPU 29 refers to the color histogram created in (2), finds the achromatic color detection range having the maximum frequency, and uses the illumination type corresponding to the achromatic color detection range at the time of shooting. Considered as a lighting type. According to the example of FIG. 9, for example, when the created color histogram is the color histogram H ₁ , the illumination type “bulb” corresponding to the achromatic color detection range C _L is regarded as the illumination type used at the time of shooting. . If the created color histogram is the color histogram H ₂ , the illumination type “first fluorescent lamp” corresponding to the achromatic color detection range C _FL1 is regarded as the illumination type used at the time of photographing.

  (4) The CPU 29 pays attention to the small areas mapped in the achromatic color detection range found in (3) among the small areas on the main image, and calculates the centroid position on the chromaticity coordinates of these small areas. To do. Then, the chromaticity corresponding to the position of the center of gravity is regarded as the illumination color being used in the current shooting scene. The calculation of the center of gravity position is preferably performed after converting the chromaticity of each small region into a correlated color temperature. The correlated color temperature is composed of a color temperature component Tc and a deviation component duv from the black body radiation locus, and the calculation when averaging a plurality of chromaticities (weighted average) is simplified.

  (5) The CPU 29 calculates the white balance adjustment amount from the correlated color temperature (Tc, duv) of the calculated center of gravity position. This white balance adjustment amount is a white balance adjustment amount for expressing an area having the same chromaticity as the correlated color temperature (Tc, duv) on the main image before white balance adjustment in an achromatic color.

  Step S120: The CPU 29 gives the calculated white balance adjustment amount to the image processing circuit 23 and gives an image processing instruction to the image processing circuit 23. The image processing circuit 23 performs white balance adjustment and other image processing on the image data of the main image in accordance with the instruction. The image data of the main image after the image processing is recorded on the storage medium 32 by the CPU 29. The above is the operation of the CPU 29 regarding photographing.

  As described above, the CPU 29 according to the present embodiment extracts the feature vector reflecting both the subject condition and the shooting condition of the shooting scene from the current shooting scene, and the feature vector and the identification obtained by supervised learning. Based on the surface, it is determined whether or not the shooting scene belongs to a specific group having similar illumination colors. As described above, the determination based on the feature amount vector reflecting both the subject condition and the shooting condition is higher performance than the determination based on the feature amount reflecting only the subject condition.

Further, the CPU 29 of the present embodiment makes a determination for each of the groups D ₁ , D ₂ , and D ₃ , and determines the chromaticity range of the color histogram to be referred to when estimating the illumination type at the time of shooting. Limit according to the result. Therefore, the illumination type is estimated with high accuracy. Therefore, the success rate of white balance adjustment is also increased.

  Further, the CPU 29 of this embodiment performs a plurality of determinations in series, and omits subsequent determination processing when it is determined that the current shooting scene belongs to a certain group. Therefore, the calculation load of the CPU 29 relating to the determination can be minimized.

  In addition, since the discrimination according to the present embodiment is performed by SVM, the discrimination capability for an unknown shooting scene is high and the generalization property is excellent.

  In addition, since the CPU 29 according to the present embodiment determines the shooting scene during a period before shooting (here, the release button is half-pressed), it is possible to reduce the amount of calculation when estimating the illumination type immediately after shooting.

[Second Embodiment]
This embodiment is a modification of the first embodiment. Here, only differences from the first embodiment will be described. Further, the number of divisions of the achromatic color detection range is 15 and the number of divisions of the group is 4. Hereinafter, each achromatic color detection range is referred to as a first achromatic color detection range, a second achromatic color detection range, a third achromatic color detection range,..., A fifteenth achromatic color detection range, These are referred to as group D ₁ , group D ₂ , group D ₃ , and group D ₄ . The relationship between these achromatic color detection ranges and groups is as follows.

Group D ₁ is a group of shooting scenes in which the illumination color belongs to any one of the fifth achromatic color detection range, the fourteenth achromatic color detection range, and the fifteenth achromatic color detection range.

Group D ₂ ... A group of shooting scenes in which the illumination color belongs to any one of the seventh achromatic color detection range, the eighth achromatic color detection range, and the ninth achromatic color detection range.

Group D ₃ ... A group of shooting scenes in which the illumination color belongs to one of the first achromatic color detection range, the second achromatic color detection range, and the third achromatic color detection range.

Group D ₄ ... A group of shooting scenes that do not belong to any of the groups D ₁ , D ₂ , and D ₃ .

In the ROM 27 of the present embodiment, the discrimination surface S ₁ , the boundary values Th _pos1 and Th _neg1 , and the discrimination regarding the group D ₂ (second discrimination) to be used in the discrimination regarding the group D ₁ (first discrimination). _{Data of} the identification surface S ₂ , boundary values Th _pos2 , Th _neg2 to be used, and identification surface S ₃ , boundary values Th _pos3 , Th _neg3 to be used in the determination (third determination) regarding the group D ₃ are stored in advance. .

  Further, the ROM 27 of the present embodiment stores in advance a first weighting coefficient table (FIG. 10), a second weighting coefficient table (FIG. 11), and a third weighting coefficient table (FIG. 12). Yes.

As shown in FIG. 10, the first weighting coefficient table stores weighting coefficients for each type of achromatic color detection range and for each value of distance d ₁ .

In the first weighting coefficient table, the achromatic color detection range having a high similarity to the group D ₁ (here, the fifth achromatic color detection range, the fourteenth achromatic color detection range, the fifteenth achromatic color detection range, etc.) Focusing on the coefficient sequence corresponding to, the coefficient corresponding to the smaller distance d ₁ has a larger value.

Also, interest in the first weighting coefficient table, (the first achromatic detection range in this case, the like 2 achromatic detection range) low similarity achromatic detection range of the group D ₁ to coefficient sequence corresponding to the Then, the coefficient corresponding to the larger distance d ₁ has a larger value.

As shown in FIG. 11, the second weighting coefficient table, each type of achromatic detection range, and for each value of the distance d ₂ stores weighting coefficients.

In this second weighting coefficient table, the achromatic color detection range having a high similarity to the group D ₂ (here, the seventh achromatic color detection range, the eighth achromatic color detection range, the ninth achromatic color detection range, etc.) When the coefficient sequence corresponding to is focused on, the coefficient corresponding to the smaller distance d ₂ has a larger value.

Also, interest in the second weighting coefficient table, (the first achromatic detection range in this case, the like 2 achromatic detection range) low similarity achromatic detection range of the group D ₂ in coefficient sequence corresponding to the Then, the coefficient corresponding to the larger value of distance d ₂ has a larger value.

As shown in FIG. 12, the third weighting coefficient table stores weighting coefficients for each type of achromatic color detection range and for each value of distance d ₃ .

In the third weighting coefficient table, a high degree of similarity achromatic detection range of the group D ₃ (first achromatic detection range in this case, the second achromatic detection range, such as the third achromatic detection range) Focusing on the coefficient sequence corresponding to, the coefficient corresponding to the smaller distance d ₃ has a larger value.

Further, in the third weighting coefficient table, an achromatic color detection range having a low similarity to the group D ₃ (here, the seventh achromatic color detection range, the eighth achromatic color detection range, the ninth achromatic color detection range, etc.) ), The coefficient corresponding to the larger value of distance d ₃ has a larger value.

  FIG. 13 is an operation flowchart of the CPU 29 regarding photographing. Again, it is assumed that the auto white balance function of the electronic camera is turned on and the recording mode of the electronic camera is set to the normal recording mode.

  Step S101: The CPU 29 determines whether or not the release button is half-pressed. If the release button is half-pressed, the process proceeds to step S102, and if the release button is not half-pressed, the step S101 is repeated.

  Step S102: The CPU 29 performs focus adjustment of the photographing lens 12, and causes the split photometric sensor 22 to start outputting an image signal of the object scene. The focus adjustment method is as described above.

  Step S103: The CPU 29 extracts a feature vector from the current shooting scene by using the SVM function. This extraction method is as described above.

Step S104: The CPU 29 calculates a distance d ₁ between the feature vector extracted in step S103 and the identification surface S ₁ by the function of the SVM.

Step S107: The CPU 29 calculates a distance d ₂ between the feature vector extracted in step S103 and the identification surface S ₂ by the function of the SVM.

Step S110: The CPU 29 calculates a distance d ₃ between the feature vector extracted in step S103 and the identification surface S ₃ by the function of the SVM.

  Step S116: The CPU 29 determines whether or not the release button has been fully pressed. If the release button is not fully pressed, the process proceeds to S117, and if the release button is fully pressed, the process proceeds to S118.

  Step S117: The CPU 29 determines whether or not the half-press of the release button has been released. If the half-press of the release button has been released, the CPU 29 stops the output of the signal from the divided photometric sensor 22 and proceeds to step S101. Returning, if the half-press of the release button continues, the process returns to step S103.

  Step S118: The CPU 29 executes an imaging process and acquires image data of the main image. The method for acquiring the image data of the main image is as described above.

Step S119 ′: The CPU 29 determines the white balance adjustment amount of white balance adjustment to be performed on the image data of the main image acquired in step S118 according to the latest determination result (distances d ₁ , d ₂ , d ₃ ). It calculates with the following procedures (1)-(7).

(1) The CPU 29 reads a coefficient corresponding to the value of the distance d ₁ from the first weighting coefficient table (FIG. 10). For example, if the value of the distance d ₁ is −200, the weighting coefficient “−16” corresponding to the first achromatic color detection range and the second achromatic color detection range are set as shown by the dotted line in FIG. The corresponding weight coefficient “−16”, the weight coefficient “−16” corresponding to the third achromatic color detection range,..., The weight coefficient “16” corresponding to the fifteenth achromatic color detection range are read. Hereinafter, these weighting coefficients sequentially _{A 1, A 2, A 3} , ..., put the A _15.

Further, the CPU 29 reads a coefficient corresponding to the value of the distance d ₂ from the second weighting coefficient data (FIG. 11). For example, if the value of the distance d ₂ is +800, the weighting coefficient “4” corresponding to the first achromatic color detection range and the second achromatic color detection range correspond to each other as shown by the dotted line in FIG. The weight coefficient “4”, the weight coefficient “4” corresponding to the third achromatic color detection range,..., The weight coefficient “−4” corresponding to the fifteenth achromatic color detection range are read out. Hereinafter, these weighting coefficients sequentially _{B 1, B 2, B 3} , ..., put the B _15.

Further, the CPU 29 reads a coefficient corresponding to the value of the distance d ₃ from the third weighting coefficient data (FIG. 12). For example, if the value of the distance d ₃ is −800, the weighting coefficient “28” corresponding to the first achromatic color detection range and the second achromatic color detection range are supported as shown by the dotted line in FIG. The weight coefficient “28”, the weight coefficient “28” corresponding to the third achromatic color detection range,..., The weight coefficient “−28” corresponding to the fifteenth achromatic color detection range are read out. Hereinafter, these weighting factors are sequentially set as C ₁ , C ₂ , C ₃ ,..., C ₁₅ .

(2) The CPU 29 applies the weighting factors A ₁ , B ₁ , C ₁ corresponding to the first achromatic color detection range among the read weighting factors to the equation of K ₁ = A ₁ + B ₁ + C _1. Thus, the weighting coefficient K ₁ related to the first achromatic color detection range is calculated. Similarly, CPU 29, by fitting the weight coefficient A _n corresponding to achromatic detection range of the n, B _n, the C _n in formula K _n = A _n + B _n + C _n, achromatic detection range of the n calculating a weighting factor K _n about (n = 2~15).

(3) The CPU 29 adjusts the values of the calculated weighting factors K _{1 to} K ₁₅ . Specifically, the CPU 29 replaces all of the weighting factors K _{1 to} K ₁₅ that are negative with zero, and then replaces each of the weighting factors K ₁ to K _{15 with} the weighting factors K _{1 to} K _15. Normalize so that the sum of ₁₅ is 1. The normalized weight coefficients K _{1 to} K ₁₅ are referred to as “normalized weight coefficients K _{1 to} K ₁₅ ”.

  (4) The CPU 29 divides the main image into a plurality of small areas, calculates the chromaticity of each small area (average chromaticity within the area), and maps these chromaticities onto the chromaticity coordinates. Each of the first achromatic color detection range to the fifteenth achromatic color detection range is defined on the chromaticity coordinates of the present embodiment.

Then, the CPU 29 calculates the number (frequency) of small regions mapped in the first achromatic color detection range to the fifteenth achromatic color detection range. However, the CPU 29 normalizes the weighting factors K ₁ , K ₂ , K ₃ ,..., K ₁₅ acquired in (3) with respect to the frequencies of the first achromatic color detection range to the fifteenth achromatic color detection range. Respectively. As a result, a weighted color histogram relating to the first achromatic color detection range to the fifteenth achromatic color detection range is created.

  (5) The CPU 29 refers to the color histogram created in (4), finds the achromatic color detection range having the maximum frequency, and uses the illumination type corresponding to the achromatic color detection range at the time of shooting. Considered as a lighting type.

  (6) The CPU 29 pays attention to the small areas mapped in the achromatic color detection range found in (5) among the small areas on the main image, and calculates the centroid position on the chromaticity coordinates of these small areas. To do. Then, the chromaticity at the position of the center of gravity is regarded as the illumination color used at the time of photographing the main image. The calculation of the center of gravity position is preferably performed after converting the chromaticity of each small region into a correlated color temperature. The correlated color temperature is composed of a color temperature component Tc and a deviation component duv from the black body radiation locus, and the calculation when averaging a plurality of chromaticities (weighted average) is simplified.

  (7) The CPU 29 calculates the white balance adjustment amount from the correlated color temperature (Tc, duv) at the calculated center of gravity position. This white balance adjustment amount is a white balance adjustment amount for expressing an area having the same chromaticity as the correlated color temperature (Tc, duv) on the main image before white balance adjustment in an achromatic color.

  Step S120: The CPU 29 gives the calculated white balance adjustment amount to the image processing circuit 23 and gives an image processing instruction to the image processing circuit 23. The image processing circuit 23 performs white balance adjustment and other image processing on the image data of the main image in accordance with the instruction. The image data of the main image after the image processing is recorded on the storage medium 32 by the CPU 29.

As described above, the CPU 29 according to the present embodiment performs determination for each of the groups D ₁ , D ₂ , D ₃ , and D ₄ , and determines the frequency of each chromaticity range of the color histogram to be referred to when estimating the illumination type at the time of shooting. On the other hand, weighting is performed according to the result of the discrimination. Therefore, in this embodiment, the illumination type is estimated with high accuracy.

Incidentally, CPU 29 of this embodiment includes a first determination result when performing weighting (distance d _1), the second determination result (the distance d _2), a third determination result (Distance d ₂ ) Is used, so that the determination process is not omitted as in the first embodiment. Therefore, the CPU 29 according to the present embodiment may execute the first determination process, the second determination process, and the third determination process in parallel.

[Other Embodiments]
In any of the above embodiments, it is assumed that no flash light emitting device is used. However, considering the possibility of using the flash light emitting device, the vector component of the feature vector includes the light emission intensity of the flash light. May be.

  In any of the above embodiments, the vector component of the feature vector includes the focal length of the photographing lens and the subject distance as photographing conditions, but includes other photographing conditions such as the aperture value of the photographing lens. Also good.

  In any of the above embodiments, the edge amount of the object scene is included as the subject condition in the vector component of the feature vector. However, other object conditions such as the contrast of the object scene may be included.

  In addition, the CPU 29 of the first embodiment sets the number of divisions of the achromatic color detection range to 8 and sets the number of group divisions to 4. Further, the CPU 29 of the second embodiment sets the number of divisions of the achromatic color detection range to 15 and sets the number of group divisions to 4. However, the combination of the division number of the achromatic color detection range and the division number of the group may be another combination.

  For example, the number of divisions of the achromatic color detection range may be 15, and the number of divisions of the group may be 7. An example of a combination of 15 achromatic color detection ranges and 7 groups is shown below.

Achromatic color detection range C _S1 ... A chromaticity range in fine weather with a low color temperature.

Achromatic color detection range C _S2 ... A chromaticity range in fine weather with a high color temperature.

Achromatic color detection range C _CL ... Cloudy chromaticity range.

Achromatic color detection range C _SH ... Shade chromaticity range.

Achromatic color detection range C _L ... Chromaticity range of the light bulb.

Achromatic color detection range C _FLWW ... Chromaticity range of light bulb color fluorescent lamp.

Achromatic color detection range C _FLW ... The chromaticity range of white fluorescent lamps.

Achromatic color detection range C _FLN ... Chromaticity range of daylight fluorescent lamps.

Achromatic color detection area C _FLD ... The chromaticity range of daylight fluorescent lamps.

Achromatic color detection area C _EXN ... The chromaticity range of daylight white fluorescent lamps with high color rendering properties.

Achromatic color detection area C _EXD ... The chromaticity range of daylight fluorescent lamps with high color rendering properties.

Achromatic color detection area C _HG1 ... The chromaticity range of the first mercury lamp.

Achromatic color detection area C _HG2 ... The chromaticity range of the second mercury lamp.

Achromatic color detection range C _SSL ... The chromaticity range of the sunset.

Achromatic color detection range C _NTL ... The chromaticity range of the sodium lamp.

Group D ₁ is a group of shooting scenes in which the illumination color belongs to one of the achromatic color detection ranges C _S1 and C _S2 .

Group D ₂ ... A group of shooting scenes in which the illumination color belongs to one of the achromatic color detection ranges C _CL and C _SH .

Group D ₃ : A group of shooting scenes in which the illumination color belongs to one of the achromatic color detection ranges C _L , C _FLWW , C _FLW .

Group D ₄ ... A group of shooting scenes in which the illumination color belongs to the achromatic color detection range C _FLN .

Group D ₅ : A group of shooting scenes in which the illumination color belongs to one of the achromatic color detection areas C _FLD , C _EXN , C _EXD .

Group D ₆ ... A group of shooting scenes in which the illumination color belongs to one of the achromatic color detection areas C _HG1 and C _HG2 .

Group D ₇ A group of shooting scenes in which the illumination color belongs to either the achromatic color detection range C _SSL or C _NTL .

In any of the above-described embodiments, learning of the SVM is performed in advance, and data such as identification surfaces (S ₁ , S ₂ , S ₃ , Th _pos1 , Th _neg1 , Th _pos2 , Th _neg2 , Th _pos3 , Th _neg2 ) is based on the assumption that it cannot be rewritten, but if the electronic camera has a manual white balance function that adjusts the white balance according to the lighting type specified by the user, the lighting type is specified. Each time the SVM learns, the data may be updated. In this case, the data storage destination of the identification surface is a rewritable memory.

  In any of the above-described embodiments, the shooting scene determination process is repeated during the half-press period of the release button, but may be performed only once immediately after the release button is half-pressed. In this case, the determination result immediately after the release button is half-pressed is held during the half-press period of the release button.

  In any of the above-described embodiments, the single-lens reflex type electronic camera that performs the monitoring of the object scene and the acquisition of the main image using different image sensors has been described. However, the compact type electronic camera that uses the common image sensor. In addition, the present invention is applicable.

  In any of the above-described embodiments, it is assumed that the recording mode of the electronic camera is the normal recording mode. However, when the recording mode is the RAW recording mode, the CPU 29 displays additional information including data obtained by the determination. The auxiliary information may be created and recorded in the storage medium 32 together with the RAW data of the main image. Thereafter, when performing development processing of RAW data, the CPU 29 may read the RAW data from the storage medium 32 and execute Step S119 (or S119 ') and Step S120 described above.

  In any of the above-described embodiments, the electronic camera executes the white balance adjustment amount calculation process, but the computer may execute part or all of the process. In that case, a program necessary for processing is installed in the computer. The installation is performed via a storage medium such as a CD-ROM or the Internet.

  Further, in the above-described second embodiment, the illumination type is estimated on the assumption that the illumination type used at the time of photographing is one. However, even if the possibility that there are a plurality of illumination types used is considered. Good. In this case, for example, step S119 'is as follows.

(1) The CPU 29 reads the coefficients A _{1 to} A ₁₅ corresponding to the value of the distance d ₁ from the first weighting coefficient table (FIG. 10), and the value of the distance d ₂ from the second weighting coefficient data (FIG. 11). reads the coefficient B ₁ .about.B ₁₅ corresponding to, read the third weighting coefficient data factors C ₁ -C ₁₅ corresponding to the value of the distance d ₃ (FIG. 12).

(2) Based on the read weighting factors A _{1 to} A ₁₅ , B _{1 to} B ₁₅ , and C _{1 to} C ₁₅ , the CPU 29 sets the weighting factor K _n related to the nth achromatic color detection range to K _n = A It is calculated by the formula _{n + B n + C n (} n = 1~15).

(3) The CPU 29 adjusts the values of the calculated weighting factors K _{1 to} K ₁₅ . Specifically, the CPU 29 replaces all of the weighting factors K _{1 to} K ₁₅ that are negative with zero, and then replaces each of the weighting factors K ₁ to K _{15 with} the weighting factors K _{1 to} K _15. Normalize so that the sum of ₁₅ is 1. The normalized weight coefficients K _{1 to} K ₁₅ are referred to as “normalized weight coefficients K _{1 to} K ₁₅ ”.

(4) The CPU 29 divides the main image into a plurality of small areas, calculates the chromaticity of each small area (average chromaticity within the area), and maps these chromaticities onto the chromaticity coordinates. Further, the CPU 29 calculates, for each achromatic color detection range, the number (frequency) of the small regions mapped in the achromatic color detection range (the first achromatic color detection range to the fifteenth achromatic color detection range) in each small region. calculate. However, the CPU 29 normalizes the weighting factors K ₁ , K ₂ , K ₃ ,..., K ₁ acquired in (3) with respect to the frequencies of the first achromatic color detection range to the fifteenth achromatic color detection range. , K ₁₅ respectively.

  (5) The CPU 29 calculates the centroid position on the chromaticity coordinates of each small area mapped to the first achromatic color detection range to the fifteenth achromatic color detection area on the main image, and the calculated centroid position Chromaticity (correlated color temperature) is regarded as the illumination color used during shooting.

(6) The CPU 29 calculates white balance adjustment amounts (gains G _B and G _R ) from the calculated correlated color temperature (Tc, duv) at the center of gravity.

It is a schematic diagram which shows the structure of the optical system of an electronic camera. It is a block diagram which shows the circuit structure of an electronic camera. It is a figure which shows the achromatic color detection range of 1st Embodiment. It is a figure which shows the example of distribution of the learning sample on vector space. Distance relationship between d ₁ and the number of samples is a diagram showing a (one example). Distance relationship between d ₂ and the number of samples is a diagram showing a (one example). Distance relationship between d ₃ and the number of samples is a diagram showing a (one example). It is an operation | movement flowchart of CPU29 of 1st Embodiment regarding imaging | photography. It is a figure explaining the chromaticity range of a color histogram. It is a figure explaining a 1st weighting coefficient table. It is a figure explaining the 2nd weighting coefficient table. It is a figure explaining a 3rd weighting coefficient table. It is an operation | movement flowchart of CPU29 of 2nd Embodiment regarding imaging | photography.

Explanation of symbols

DESCRIPTION OF SYMBOLS 11 ... Camera body, 16 ... Color imaging device, 16a ... AFE, 22 ... Divided photometry sensor, 22a ... A / D conversion circuit, 23 ... Image processing circuit, 24 ... Buffer memory, 25 ... Recording interface, 26 ... Operation switch, 29 ... CPU, 28 ... RAM, 27 ... ROM, 31 ... Bus

Claims (14)

  From the shooting scene to be discriminated, a feature vector that reflects both the subject condition and the shooting condition of the shooting scene is extracted, and based on the feature vector and the discrimination criterion calculated in advance by supervised learning, A discriminating means for discriminating whether or not the shooting scene belongs to a specific group having similar illumination colors;
  The vector component of the feature vector includes
  Contains lens information of the taking lens
  A color imaging apparatus characterized by the above. From the shooting scene to be discriminated, a feature vector that reflects both the subject condition and the shooting condition of the shooting scene is extracted, and based on the feature vector and the discrimination criterion calculated in advance by supervised learning, A discriminating means for discriminating whether or not the shooting scene belongs to a specific group having similar illumination colors;
  An estimation means for estimating an illumination color at the time of shooting based on a color histogram of an image shot in the shooting scene;
  The estimation means includes
  The color range of the color histogram used for the estimation is limited according to the result of discrimination performed by the discrimination means.
  A color imaging apparatus characterized by the above. From the shooting scene to be discriminated, a feature vector that reflects both the subject condition and the shooting condition of the shooting scene is extracted, and based on the feature vector and the discrimination criterion calculated in advance by supervised learning, A discriminating means for discriminating whether or not the shooting scene belongs to a specific group having similar illumination colors;
The vector component of the feature vector includes
A color imaging apparatus comprising a color of an object scene and a lens position of a photographing lens. From the shooting scene to be discriminated, a feature vector that reflects both the subject condition and the shooting condition of the shooting scene is extracted, and based on the feature vector and the discrimination criterion calculated in advance by supervised learning, A discriminating means for discriminating whether or not the shooting scene belongs to a specific group having similar illumination colors;
The discrimination means includes
A color imaging device characterized by being a support vector machine. From the shooting scene to be discriminated, a feature vector that reflects both the subject condition and the shooting condition of the shooting scene is extracted, and based on the feature vector and the discrimination criterion calculated in advance by supervised learning, A discriminating means for discriminating whether or not the shooting scene belongs to a specific group having similar illumination colors;
The discrimination means includes
The color imaging apparatus, wherein the determination is performed for each of a plurality of specific groups having different illumination colors. The color imaging device according to claim 5 ,
The discrimination means includes
A color imaging apparatus characterized by sequentially performing discrimination regarding each of the plurality of specific groups and omitting subsequent discrimination processing when the discrimination result is “positive”. The color imaging device according to claim 5 or 6 ,
The plurality of specific groups are:
Groups whose lighting color belongs to the chromaticity range of low color temperature lighting, groups whose lighting color belongs to the chromaticity range of fluorescent lamps or mercury lamps, chromaticity of fluorescent lamps with natural color rendering or natural sunlight A color imaging apparatus characterized by being any three of a group belonging to a range and a group having an illumination color belonging to a shaded or cloudy chromaticity range. The color imaging device according to claim 5 or 6 ,
The plurality of specific groups are:
A group in which the illumination color belongs to the chromaticity range of clear sky, a group in which the illumination color belongs to the shaded chromaticity range, a group in which the illumination color belongs to the chromaticity range of the low-temperature fluorescent lamp or bulb, and the illumination color , A group that belongs to the chromaticity range of the medium color temperature fluorescent lamp, a group that the illumination color belongs to the chromaticity range of the high color temperature fluorescent lamp, a group that the illumination color belongs to the chromaticity range of the mercury lamp, and the illumination color A color imaging apparatus characterized in that any one of the groups belonging to the chromaticity range of the low color temperature illumination. The color imaging device according to any one of claims 5 to 8 ,
An estimation means for estimating the type of illumination at the time of shooting based on a color histogram of an image shot in the shooting scene;
The color imaging apparatus, wherein the estimation unit limits a color range of the color histogram according to a result of determination performed by the determination unit. The color imaging device according to any one of claims 5 to 8 ,
An estimation means for estimating the type of illumination at the time of shooting based on a color histogram of an image shot in the shooting scene;
The color estimation apparatus, wherein the estimation unit weights the frequency of each color range of the color histogram according to a result of determination performed by the determination unit.   In the color imaging device according to any one of claims 1, 2, and 4 to 10,
  The vector component of the feature vector includes
  Includes the field color and the lens position of the taking lens
  A color imaging apparatus characterized by the above.   In the color imaging device according to any one of claims 1 to 3 and claims 5 to 11,
  The discrimination means includes
  It is a support vector machine
  A color imaging apparatus characterized by the above. In the color imaging device according to any one of claims 1 to 12 ,
The vector component of the feature vector includes
A color imaging apparatus comprising an edge amount existing in the object scene. In the color imaging device according to any one of claims 1 to 13 ,
The discrimination means includes
A color imaging apparatus, wherein the discrimination is performed in a period before photographing.

Images